ComfyUI Node
🐓 Bawk Sampler
🐓 All-in-one FLUX sampler with txt2img/img2img, smart validation, and built-in VAE decoding
🐓 Bawk Sampler
- model
- conditioning
- vae
- input_image
- images
- latent
◄resolutionFLUX Optimal - 1024x1024 - 1.0MP (Recommended)►
◄batch_size4►
◄seed0►
◄samplereuler►
◄schedulerbeta►
◄steps30►
◄guidance3.5►
◄max_shift1.15►
◄base_shift0.50►
◄denoise1.00►
◄use_custom_resolutionfalse►
◄custom_width1920►
◄custom_height1080►
CategoryBawkNodes/sampling
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| conditioning | CONDITIONING | — | |
| vae | VAE | — | |
| resolution | COMBO | FLUX Optimal - 1024x1024 - 1.0MP (Recommended) | Resolution presets optimized for FLUX - 1024x1024 is the sweet spot for quality/speed |
| batch_size | INT | 41–64 | Number of images to generate |
| seed | INT | 00–18446744073709550000 | Random seed for generation |
| sampler | COMBO | euler | Sampling method for generation |
| scheduler | COMBO | beta | Noise scheduling method |
| steps | INT | 301–100 | Sampling steps - FLUX optimal: 30 (20=fast, 40=quality) |
| guidance | FLOAT | 3.50–20 | Guidance scale - FLUX recommended: 3.5 (balanced), 2.0 (creative), 7.0 (structured) |
| max_shift | FLOAT | 1.150–2 | Max shift for FLUX - 1.15 is optimal (higher=more coherent, lower=more varied) |
| base_shift | FLOAT | 0.500–2 | Base shift for FLUX - 0.5 is optimal for most cases |
| denoise | FLOAT | 1.000–1 | Denoise strength - Use 1.0 for text-to-image, 0.6-0.9 for image-to-image |
| use_custom_resolution | BOOLEAN | false | Enable custom width/height instead of presets |
| input_imageopt | IMAGE | Input image for img2img generation. Leave empty for text-to-image mode. | |
| custom_widthopt | INT | 192064–4096 | Custom width (must be multiple of 64). Only used when custom resolution is enabled. |
| custom_heightopt | INT | 108064–4096 | Custom height (must be multiple of 64). Only used when custom resolution is enabled. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| latent | LATENT | — |